INDEX

Explanations

examples and illustrative code

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myös

-1.17

diging

-1.14

hotra

-1.02

 ALSO

-0.99

utenants

-0.98

 الأخرى

-0.97

 также

-0.96

 also

-0.96

 همچنین

-0.96

蓁

-0.95

POSITIVE LOGITS

 example

3.33

 examples

2.64

Example

2.17

 Example

2.11

example

2.11

 Examples

1.88

EXAMPLE

1.80

examples

1.80

Examples

1.78

 ejemplo

1.66

Activations Density 0.126%